import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

def man_u(row):
    if row['HomeTeam']== "Man United":
        return row['FTHG']
    else:
        return row['FTAG']

df['MU_goals'] = df.apply(man_u,axis=1)

team ="Man United"
df["Points"]=0

def calpoints(row):
    if row['HomeTeam']==team and row['FTR']=='H':
        return 3
    elif row['AwayTeam']==team and row['FTR']=='A':
        return 3
    elif row['FTR']=='D':
        return 1
    return 0
df["Points"] = df.apply(calpoints,axis=1)

df.to_csv("14-21.csv",index=False)

df = pd.read_csv("14-21.csv")
df.head()

df.drop(columns = ['Referee'],inplace =True)

df.head(39)

matches_per_season = df.groupby('Season').size()
print(matches_per_season)

Season
14-15    38
15-16    38
16-17    38
17-18    38
18-19    16
19-20    26
20-21    38
dtype: int64

df.drop(columns = ['HTR'],inplace = True)

df.head()

df.to_csv("14-21.csv",index=False)

#goals per season
goals_season = df.groupby('Season')['MU_goals'].sum()
print(goals_season)

Season
14-15    62
15-16    49
16-17    54
17-18    68
18-19    28
19-20    38
20-21    73
Name: MU_goals, dtype: int64

#how many goals were scored during each match 
y = goals_season/matches_per_season
print(y)

Season
14-15    1.631579
15-16    1.289474
16-17    1.421053
17-18    1.789474
18-19    1.750000
19-20    1.461538
20-21    1.921053
dtype: float64

# total goals per season scored at home games 
home_games = df[df['HomeTeam']=='Man United']
h_goals = home_games.groupby('Season')['FTHG'].sum()
print(h_goals)

Season
14-15    41
15-16    27
16-17    26
17-18    38
18-19    14
19-20    24
20-21    38
Name: FTHG, dtype: int64

# total goals per season scored at away games 

a_goals = goals_season-h_goals
print(a_goals)

Season
14-15    21
15-16    22
16-17    28
17-18    30
18-19    14
19-20    14
20-21    35
dtype: int64

#Goals scored in the first half

df['halft_goals'] = df.apply(lambda row: row['HTHG'] if row['HomeTeam']=='Man United' else row['HTAG'],axis=1)
first_half_goals = df.groupby('Season')['halft_goals'].sum()
print(first_half_goals)

Season
14-15    33
15-16    21
16-17    28
17-18    29
18-19    15
19-20    20
20-21    28
Name: halft_goals, dtype: int64

#goals scored in the second half

sec_half_goals = goals_season-first_half_goals
print(sec_half_goals)

Season
14-15    29
15-16    28
16-17    26
17-18    39
18-19    13
19-20    18
20-21    45
dtype: int64

df.groupby('Season')[['HY','AY']].sum()

#yellow card at home and away

df['mu_y_h'] = np.where(df['HomeTeam']=='Man United',df['HY'],0)
df['mu_y_a'] = np.where(df['AwayTeam']=='Man United',df['AY'],0)

df['mu_r_h'] = np.where(df['HomeTeam']=='Man United',df['HR'],0)
df['mu_r_a'] = np.where(df['AwayTeam']=='Man United',df['AR'],0)

yellow_home =df.groupby('Season')['mu_y_h'].sum()
yellow_away =df.groupby('Season')['mu_y_a'].sum()
red_home =df.groupby('Season')['mu_r_h'].sum()
red_away =df.groupby('Season')['mu_r_a'].sum()
print(f"yellow cards at home\n{yellow_home}\n")
print(f"yellow cards away\n{yellow_away}\n")
print(f"red cards at home\n{red_home}\n")
print(f"red cards away\n{red_away}\n")

yellow cards at home
Season
14-15    31
15-16    29
16-17    36
17-18    29
18-19    14
19-20    22
20-21    36
Name: mu_y_h, dtype: int64

yellow cards away
Season
14-15    33
15-16    36
16-17    40
17-18    35
18-19    19
19-20    28
20-21    28
Name: mu_y_a, dtype: int64

red cards at home
Season
14-15    1
15-16    0
16-17    1
17-18    0
18-19    0
19-20    0
20-21    1
Name: mu_r_h, dtype: int64

red cards away
Season
14-15    4
15-16    1
16-17    1
17-18    1
18-19    2
19-20    0
20-21    0
Name: mu_r_a, dtype: int64

        mu_y_h  mu_y_a
Season                
14-15       38      38
15-16       38      38
16-17       38      38
17-18       38      38
18-19       16      16
19-20       26      26
20-21       38      38
        mu_r_h  mu_r_h
Season                
14-15        1       1
15-16        0       0
16-17        1       1
17-18        0       0
18-19        0       0
19-20        0       0
20-21        1       1

df['MU_y'] = df.apply(lambda row: row['HY'] if row['HomeTeam']=='Man United' else row['AY'],axis=1)
df['MU_r'] = df.apply(lambda row: row['HR'] if row['HomeTeam']=='Man United' else row['AR'],axis=1)

yellow_season = df.groupby('Season')['MU_y'].sum()
red_season = df.groupby('Season')['MU_r'].sum()


print(yellow_season)
print(red_season)

Season
14-15    64
15-16    65
16-17    76
17-18    64
18-19    33
19-20    50
20-21    64
Name: MU_y, dtype: int64
Season
14-15    5
15-16    1
16-17    2
17-18    1
18-19    2
19-20    0
20-21    1
Name: MU_r, dtype: int64

#shots taken vs shots on target

df['MU_S'] = df.apply(lambda row: row['HS'] if row['HomeTeam']=='Man United' else row['AS'],axis=1)
df['MU_ST'] = df.apply(lambda row: row['HST'] if row['HomeTeam']=='Man United' else row['AST'],axis=1)

shots_season = df.groupby('Season')['MU_S'].sum()
shots_tar_season = df.groupby('Season')['MU_ST'].sum()


print(f"total shots taken \n{shots_season}\n")
print(f"shots on target \n{shots_tar_season}\n")

perc = (shots_tar_season/shots_season)*100
print(f"overall percentage of shorts on target /n{perc}%")

total shots taken 
Season
14-15    509
15-16    430
16-17    589
17-18    513
18-19    210
19-20    381
20-21    521
Name: MU_S, dtype: int64

shots on target 
Season
14-15    179
15-16    143
16-17    210
17-18    181
18-19    100
19-20    146
20-21    212
Name: MU_ST, dtype: int64

overall percentage of shorts on target /nSeason
14-15    35.166994
15-16    33.255814
16-17    35.653650
17-18    35.282651
18-19    47.619048
19-20    38.320210
20-21    40.690979
dtype: float64%

#TOTAL GOALS OF EACH SEASON OF MAN UNITED

plt.plot(goals_season)
plt.grid(axis='y')
plt.title('Man United Goals Per Season')
plt.xlabel('Seasons')
plt.ylabel('Goals')

Text(0, 0.5, 'Goals')

#GOALS SCORED IN FIRST HALF VS SSECOND HALF FOR EACH SEASON


seasons = first_half_goals.index
x = range(len(seasons))  

plt.bar(x, first_half_goals, width=0.4, label='First Half Goals', align='center')
plt.bar([i+0.4 for i in x], sec_half_goals, width=0.4, label='Second Half Goals', align='center')

plt.xticks([i + 0.2 for i in x], seasons, rotation=45)
plt.ylabel('Goals')
plt.title('Man United: First Half vs Second Half Goals per Season')
plt.legend()
plt.tight_layout()
plt.show()

!pip install plotly

Collecting plotly
  Downloading plotly-6.0.1-py3-none-any.whl.metadata (6.7 kB)
Collecting narwhals>=1.15.1 (from plotly)
  Downloading narwhals-1.38.0-py3-none-any.whl.metadata (9.3 kB)
Requirement already satisfied: packaging in /Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages (from plotly) (24.2)
Downloading plotly-6.0.1-py3-none-any.whl (14.8 MB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 14.8/14.8 MB 137.2 kB/s eta 0:00:0000:0100:03
Downloading narwhals-1.38.0-py3-none-any.whl (338 kB)
Installing collected packages: narwhals, plotly
Successfully installed narwhals-1.38.0 plotly-6.0.1

[notice] A new release of pip is available: 25.0.1 -> 25.1.1
[notice] To update, run: pip install --upgrade pip

#home goals vs away goals per season.

import plotly.express as px
import pandas as pd

# Make a new DataFrame for heatmap
df_heat = pd.DataFrame({
    'Season': list(h_goals.index) * 2,
    'Type': ['Home'] * len(h_goals) + ['Away'] * len(h_goals),
    'Goals': list(h_goals.values) + list(a_goals.values)
})

fig = px.density_heatmap(df_heat, x="Season", y="Type", z="Goals",
                         color_continuous_scale="Viridis", text_auto=True)
fig.show()

#shots vs shots on target

import plotly.graph_objects as go


# Compute the difference: shots that were NOT on target
shots_off_target = shots_season - shots_tar_season


fig = go.Figure(data=[
    go.Bar(name='ON Target', y=shots_season.index, x=shots_tar_season, orientation='h'),
    go.Bar(name='OFF Target', y=shots_season.index, x=shots_off_target, orientation='h')
])


# Customize layout
fig.update_layout(
    barmode='stack',
    title='Man United: Total Shots vs Shots on Target per Season',
    xaxis_title='Season',
    yaxis_title='Number of Shots',
    template='plotly_white'
)

fig.show()

import plotly.express as px

fig = px.pie(perc,values=perc.values,names=perc.index,color_discrete_sequence=px.colors.sequential.Viridis)
fig.show()

dot_data = pd.DataFrame({
    'Season': yellow_home.index,
    'Yellow (Home)': yellow_home.values,
    'Yellow (Away)': yellow_away.values,
    'Red (Home)': red_home.values,
    'Red (Away)': red_away.values
})


dot_data_melted = dot_data.melt(id_vars='Season', var_name='Card Type', value_name='Count')

# Dot Plot
fig = px.scatter(
    dot_data_melted,
    x='Count',
    y='Season',
    color='Card Type',
    symbol='Card Type',
    title='Man United: Yellow and Red Cards (Home vs Away)',
    template='plotly_white'
)

fig.update_traces(marker=dict(size=12))
fig.show()

	Season	Date	HomeTeam	AwayTeam	FTHG	FTAG	FTR	HTHG	HTAG	HS	...	HF	AF	HC	AC	HY	AY	AR	Points	MU_goals
0	14-15	8/16/2014	Man United	Swansea	1	2	A	0	1	14	...	14	20	4	0	2	4	0	0	1
1	14-15	8/24/2014	Sunderland	Man United	1	1	D	1	1	11	...	10	15	4	4	0	2	0	1	1
2	14-15	8/30/2014	Burnley	Man United	0	0	D	0	0	9	...	10	14	3	6	2	2	0	1	0
3	14-15	9/14/2014	Man United	QPR	4	0	H	3	0	19	...	11	8	3	1	1	0	0	3	4
4	14-15	9/21/2014	Leicester	Man United	5	3	H	1	2	15	...	11	9	2	4	1	1	1	0	3

	HY	AY
Season
14-15	64	75
15-16	55	65
16-17	67	77
17-18	64	68
18-19	30	34
19-20	54	56
20-21	75	51

¶